Qwen 3 Models — Page 51

qwen3_1.7b_easy_rl_ours_adv_fixed_gamma_995_98_ori_norm

Diploy-8B-Base

Qwen3-0.6B-Gensyn-Swarm-pudgy_tropical_snail

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_5__global_step_1776

Qwen3-0.6B-GPQA-Learning

self-debate-exp-Qwen3-4B-Base-majority_n4_l2048-DAPO_n8_bs256_long8-step200

affine-1-5ETyoog2ttXGSu5UhxhrLtjdL1BSbo2SeELdFAp1YBimQuq9

qwen3_1.7b_sudoku_one_action_easy_11_20_epoch2

qwen3_1.7b_sudoku_multi_action_easy_11_20

qwen3_1.7b_new_sudoku_one_action_B_sft_lr_5e_6__step_3324

qwen3_1.7b_new_sudoku_one_action_C_sft_lr_5e_6__step_5004

qwen3-4b-dpo-hh-rlhf-reversed

Qwen3-0.6B-Reverse-Text-RL

Fun-ASR-MLT-Nano-2512-vllm

tony-seba-qwen3-merged

Affine-20-5FWcW3wkNg9E2GYPhZYsAEMLU83NfDXSGShLwZ2dRLJKz2kB

qwen3-4b_grpo_skywork_code_sandbox_2-global_step_800

Qwen3-0.6B-Gensyn-Swarm-lively_darting_penguin

qwen3-1.7b-base-adam-1e-6-bs128-kl0.0-global_step_20

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_180

qwen3-4b-base-svd-muon-adam-1e-6-adamlr-1e-6-bs128-kl0.0-global_step_120

qwen3-4b_grpo_skywork_math-global_step_200

qwen3_1.7b_rush_hour_one_move_4_9

qwen3_instruct_8b

qwen3-4b-sft-test

Qwen3-1.7B-CCC-merged-cp6-LR1e-4

vpt_gen-0.6b

qwen3-4b-instruct-meta-GRPO-2

Qwen3-4B-Base-SFT-20260120102752

qwen3-1.7b-dspo-no-sft-exp2

dpo-qwen-cot-merged

DPO_v1_20260207

dpo-qwen-cot-merged-V1

llm2025_main_merged_dpo03

sched-v4

sft-dpo-qwen-cot-merged

dpo-qwen-cot-merged

vazhi-v5_3

dpo-qwen-cot-merged-from-sft-adapter-38-1

qwen3-v2-fp16

dpo-qwen-cot-merged

qwen3-1.7b-bilingual-amr-sft-v2